© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15562
    Prev
    Next
    INDEX
    Explanations

    github.com import package.name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    0.51
    recogn
    0.44
    ad
    0.42
     types
    0.40
    de
    0.40
    2
    0.40
     inter
    0.40
    types
    0.39
    the
    0.39
     different
    0.39
    POSITIVE LOGITS
     cendré
    0.39
     awalnya
    0.38
    oyeva
    0.37
    蓁
    0.36
    Says
    0.36
    Antaeotricha
    0.36
    െന്നാണ്
    0.35
     vatth
    0.35
    िवार
    0.35
    但我
    0.35
    Activations Density 0.004%

    No Known Activations